Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add s977043/river-review --skill knowledge-to-code-alignmentgit clone --depth 1 https://github.com/s977043/river-reviewWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/s977043/river-review/knowledge-to-code-alignment)<a href="https://agentmods.dev/skills/s977043/river-review/knowledge-to-code-alignment"><img src="https://agentmods.dev/badge/skills/s977043/river-review/knowledge-to-code-alignment/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/s977043/river-review/knowledge-to-code-alignment"><img src="https://agentmods.dev/badge/skills/s977043/river-review/knowledge-to-code-alignment.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00286 | $0.04951 |
| Opus 5 | $0.00143 | $0.02475 |
| Sonnet 5 | $0.00057 | $0.00990 |
| Haiku 4.5 | $0.00029 | $0.00495 |
Grade A, and why
Knowledge-to-Code Alignment 新知識のコード反映・設計知識の保全 scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Origin / 由来
inspired by:
- https://agilejourney.uzabase.com/entry/2026/07/16/103000 — リファクタリングを単なるコード整理ではなく、開発によって更新されたチームの理解と、コードが表現する過去の理解との差分を同期する活動として捉える論。
上記は観測された考え方の紹介であり、本文の転載・著者による endorsement を含まない（nominative fair use）。命名は skills/README.md Naming に従い value を表す新規名として付与した。
Pattern declaration
Primary pattern: Reviewer Secondary patterns: Inversion Why: 新知識のコード反映と設計知識の保全は意味的判断が主だが、Knowledge Delta（比較基準）が discover できない差分では実行を止めるゲートが必要。
Goal / 目的
リファクタリング・機能変更の diff に対し、次を diff-time で確認する。テストが通るだけでは見つからない「設計知識の消失」と「古い理解の残存」を検出する。
- 新知識の反映: 今回新しく得た要求・ドメイン知識・制約（Knowledge Delta）が、命名（naming）と責務（responsibility）へ反映されているか。
- 境界の表現: モジュール/関数の境界（boundary）が、古い理解ではなく現在の understanding を表現しているか。意図がコメントだけで補足され、コード構造へ反映されていない状態になっていないか。
- 設計知識の保全: ADR・過去 PR・コメントに残る過去の design history（設計判断・制約・例外・運用知識）を、今回の変更で失っていないか。
report-only。finding/question のみを出力し、自動修正・自動マージはしない。
Non-goals / 扱わないこと（委譲表）
- ドメイン用語の一貫性: 同一概念の別名・別概念の同名という命名ドリフトは
ubiquitous-language-namingが担う。本 skill は用語の一貫性ではなく、新知識が命名・責務へ反映されたか（Knowledge Delta の反映）を見る。 - 集約・コンテキスト境界の設計判断: 境界づけられたコンテキスト・集約境界の妥当性は
bounded-context-languageが artifact ベースで担う。本 skill は diff 上の関数/モジュール境界が現在の理解を表現するかに集中する。 - 投機的抽象化・caller special-case: 将来予測に基づく過剰抽象化・共有基盤への継ぎ接ぎは
altitude-generalizationが担う。本 skill は「新知識の反映不足」「設計知識の消失」を見る。 - スコープ逸脱・前提破壊: 指摘対応ループでのスコープ creep・成立済み前提の破壊は
fix-scope-integrityが担う。 - 振る舞い変更と構造変更の分離: 外部挙動維持・振る舞い/構造変更の混在判定は
behavior-structure-separation（sibling）が担う。本 skill は挙動ではなく知識の反映・保全を見る。 - 完了主張の反証: 「全部置換した」「-N%削減」等の完了主張の grep 反証は
refactor-claim-auditが担う。
Pre-execution Gate / 実行前ゲート
このスキルは以下の条件がすべて満たされない限り NO_REVIEW を返す。
- inputContext に
diffが含まれている。 - 差分がリポジトリ内で実行されるコードに触れる（docs・コメントのみの差分は対象外）。
- Knowledge Delta の signal が diff から discover できる。具体的には次のいずれか: diff の追加/削除された hunk・差分内のコメント（
// ...・# ...等）・差分内に現れる issue/ADR 参照（#1573・ADR-012等）・コミットや PR 本文が供給されている場合はその記述に、「新しく得た要求・ドメイン知識・制約」または「過去の設計判断・制約」が読み取れる。PlanGate がKnowledge Deltaを提供する場合はそれを入力とする。 - ビルド成果物・生成物（
dist/**・*.map・lockfile・自動生成 manifest）は Gate 判定からもレビュー対象からも除外する。
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 192 lines · 286 tokens per session scan A e0c555787045
Knowledge-to-Code Alignment 新知識のコード反映・設計知識の保全 is a skill published in the GitHub repository s977043/river-review (3 stars, last pushed today), licensed MIT. It adds 286 tokens to every session and 4,951 once invoked, about $0.0014 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
logic-health
Sweep a directory, module, or full codebase for logic correctness and produce a scored health dashboard with systemic patterns. Trigger when the user requests a health view — "audit the whole codebase", "health check", "health overview", "logic health overview", "audit src/", "audit auth and payments modules", "where…
logic-diff
Compare two code versions for semantic equivalence via semi-formal tracing of both versions side-by-side. Trigger when the user shares a refactor, rewrite, migration, or A/B implementation and wants to confirm behavior is unchanged — "did I break anything", "is this equivalent", "are these equivalent", "semantically…
omnicheck-gitlab
Use when checking if MR review findings have been applied — verifies both OmniForge-generated and human reviewer comments against the current diff, posts nudge replies on unaddressed threads.
omnicheck-github
Use when checking if PR review findings have been applied — verifies both OmniForge-generated and human reviewer comments against the current diff, posts nudge replies on unaddressed threads.
omnicreate-gitlab
Use when creating a GitLab merge request (OmniForge). Auto-populates title and description from commits, supports draft MRs, labels, assignees, reviewers, and issue linking.
adversarial-review
Cross-host adversarial review of implementation plans, code/diffs/configs, or prompts/skill definitions. Classifies the artifact, routes the heavy critique to the agent that is NOT the host, cross-validates against independent host-side analysis, and returns material findings with severity and a verdict. Plan/code…